{"id":"W2964087600","doi":"","title":"Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Relation (database); Artificial intelligence; Task (project management); Convolutional neural network; Abstraction; Artificial neural network; Representation (politics); Machine learning; Deep learning; Layer (electronics); Recurrent neural network; SemEval; Deep neural networks; External Data Representation; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001410785,0.00009525834,0.00006928528,0.00005232442,0.0001000396,0.00004527911,0.0007680641,0.00005178945,0.000009487328],"category_scores_gemma":[0.00001337599,0.00007633552,0.00001622553,0.0002844305,0.00003276295,0.001503116,0.0001991799,0.00007545855,0.000009412173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108513,"about_ca_system_score_gemma":0.00002142448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001930884,"about_ca_topic_score_gemma":0.00002945924,"domain_scores_codex":[0.9989984,0.00006654362,0.0001097271,0.0005973895,0.00005838868,0.0001695356],"domain_scores_gemma":[0.9987773,0.0000575949,0.0001294987,0.00090868,0.00005817594,0.00006870035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002668106,0.0002573958,0.03911937,0.0000234188,0.000110845,0.00003936413,0.0004261612,0.1704315,0.00704986,0.2049581,0.001573949,0.5757433],"study_design_scores_gemma":[0.0005422141,0.00004699991,0.002416534,0.00001146562,0.00001340708,0.000001493517,0.0000204232,0.9963212,0.00004262094,0.0003359453,0.0001269172,0.0001207666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08546837,0.00001742331,0.9136775,0.0002966246,0.0001581234,0.000125768,0.000002880635,0.000106734,0.0001466136],"genre_scores_gemma":[0.9964454,0.00003217164,0.0031771,0.00004295438,0.00003366062,4.883261e-7,0.00003231082,0.00000598291,0.0002298981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9109771,"threshold_uncertainty_score":0.3112872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09306325500152063,"score_gpt":0.1957738082389306,"score_spread":0.10271055323741,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}